60,852 Hits in 5.1 sec

Accurate Hand Detection from Single-Color Images by Reconstructing Hand Appearances

Chi Xu, Wendi Cai, Yongbo Li, Jun Zhou, Longsheng Wei
2019 Sensors  
To tackle this problem, an accurate hand detection method is proposed to reliably detect multiple hands from a single color image using a hybrid detection/reconstruction convolutional neural networks (  ...  CNN) framework, in which regions of hands are detected and appearances of hands are reconstructed in parallel by sharing features extracted from a region proposal layer, and the proposed model is trained  ...  ., Z.Z. and J.W. from Hubei Key Laboratory of Advanced Control and School of Automation, China University of Geosciences. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s20010192 pmid:31905746 pmcid:PMC6982909 fatcat:pbpqzetwsbc6hn2cuawn7lutpe

Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image

Chi Xu, Yunkai Jiang, Jun Zhou, Yi Liu
2021 Sensors  
Experimental results show that, the gesture recognition accuracy of ours is significantly boosted by leveraging the knowledge learned from the hand pose estimation task.  ...  Our approach detects the foreground hand, recognizes the hand gesture, and estimates the corresponding 3D hand pose simultaneously.  ...  Foreground Hand Detection Taking a single color image as input, we detect all hand instances and distinguish the foreground hand instances from the background hand instances.  ... 
doi:10.3390/s21031007 pmid:33540786 fatcat:e37lg4ixcjc7zdz3jq2elfzv2a

LISA: Learning Implicit Shape and Appearance of Hands [article]

Enric Corona, Tomas Hodan, Minh Vo, Francesc Moreno-Noguer, Chris Sweeney, Richard Newcombe, Lingni Ma
2022 arXiv   pre-print
The model can capture accurate hand shape and appearance, generalize to arbitrary hand subjects, provide dense surface correspondences, be reconstructed from images in the wild and easily animated.  ...  We experimentally demonstrate that LISA can accurately reconstruct a dynamic hand from monocular or multi-view sequences, achieving a noticeably higher quality of reconstructed hand shapes compared to  ...  Acknowledgements: This work is supported in part by the Spanish government with the project MoHuCo PID2020-120049RB-I00.  ... 
arXiv:2204.01695v1 fatcat:53v7sunsjze6ndb5k2exeqz6x4

Structured Light Illumination Methods for Continuous Motion Hand and Face-computer Interaction [chapter]

Charles J., Laurence G., Daniel L.
2008 Human Computer Interaction: New Developments  
Color-multiplexing simply combines individual patterns from some multi-pattern technique into a single pattern by coloring each differently.  ...  Fingertip Detection The fingertip detection is accomplished globally by using a correlation filter designed to detect fingertips and suppress other regions of the hand.  ... 
doi:10.5772/5863 fatcat:6yksactykva33dpxudzivenil4

Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained Environments

Chi Xu, Jun Zhou, Wendi Cai, Yunkai Jiang, Yongbo Li, Yi Liu
2020 Sensors  
Three-dimensional hand detection from a single RGB-D image is an important technology which supports many useful applications.  ...  To tackle this problem, we propose a 3D hand detection approach which improves the robustness and accuracy by adaptively fusing the complementary features extracted from the RGB-D channels.  ...  Acknowledgments: We thank the volunteers who help us collect CUG Hand dataset.  ... 
doi:10.3390/s20216360 pmid:33171831 pmcid:PMC7664645 fatcat:rwobugjecnhutlzjzdubpq3qmm

Consistent 3D Hand Reconstruction in Video via self-supervised Learning [article]

Zhigang Tu, Zhisheng Huang, Yujin Chen, Di Kang, Linchao Bao, Bisheng Yang, Junsong Yuan
2022 arXiv   pre-print
We present a method for reconstructing accurate and consistent 3D hands from a monocular video.  ...  Thus we propose S^2HAND, a self-supervised 3D hand reconstruction model, that can jointly estimate pose, shape, texture, and the camera viewpoint from a single RGB input through the supervision of easily  ...  for hand pose and shape estimation from single RGB images.  ... 
arXiv:2201.09548v1 fatcat:sv6463vtzndkdlv2jhsq2itpim

Determining Occlusions from Space and Time Image Reconstructions

Juan-Manuel Perez-Rua, Tomas Crivelli, Patrick Bouthemy, Patrick Perez
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
The key issue is now to determine how well a pixel in the first image can be "reconstructed" from co-located colors in the next image.  ...  With this in mind, we propose a novel approach to occlusion detection where visibility or not of a point in next frame is formulated in terms of visual reconstruction.  ...  On the other hand, ζ 1 captures the intrinsic appearance of I 1 revisited from its own perspective for every x on the image grid Ω.  ... 
doi:10.1109/cvpr.2016.154 dblp:conf/cvpr/Perez-RuaCBP16 fatcat:mgakxklzyzam3ijd353fxfqtim

Hand Posture Segmentation, Recognition and Application for Human-Robot Interaction [chapter]

Xiaoming Yin, Ming Xie
2007 Human Robot Interaction  
The first group of models is based on appearance of the hand in the visual images.  ...  Gestures are modeled by relating the appearance of any gesture to that of the set of predefined template gestures [Pavlovic et al., 1996 ] [Ahmad et al., 1997 .  ...  In this section, we propose to infer 3D information of the hand from the images taken from different viewpoints and reconstruct hand gestures using 3D reconstruction techniques.  ... 
doi:10.5772/6097 fatcat:tccxqupb4bb7vp6el7ldn72nza

Robust Segmentation and Decoding of a~Grid Pattern for Structured Light [chapter]

Jordi Pagès, Joaquim Salvi, Carles Matabosch
2003 Lecture Notes in Computer Science  
Moreover, not only the cross-points of the grid can be reconstructed but also the pixels belonging to vertical and horizontal slits.  ...  Therefore, cross points can be reconstructed more accurately by intersecting the equations of two 3D lines.  ...  Then, a set of well distributed pixels on the image can be reconstructed with a single projection.  ... 
doi:10.1007/978-3-540-44871-6_80 fatcat:v5oiw3jt5bc7tiawqrxowovnve

Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo [article]

Paschalis Panteleris Institute of Computer Science, FORTH, Computer Science Department, University of Crete)
2017 arXiv   pre-print
Unfortunately, this does not work well in practice because the stereo-based, dense 3D reconstruction of hands is far less accurate than the one obtained by RGBD cameras.  ...  Our approach bypasses 3D reconstruction and follows a completely different route: 3D hand tracking is formulated as an optimization problem whose solution is the hand configuration that maximizes the color  ...  Therefore, it is quite likely that the corresponding 2D image points will have inconsistent appearance (e.g., different color).  ... 
arXiv:1705.05301v1 fatcat:i7vylpk6yve3rgn4qdr653u2cm

Back to RGB: 3D Tracking of Hands and Hand-Object Interactions Based on Short-Baseline Stereo

Paschalis Panteleris, Antonis Argyros
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
Unfortunately, this does not work well in practice because the stereo-based, dense 3D reconstruction of hands is far less accurate than the one obtained by RGBD cameras.  ...  Our approach bypasses 3D reconstruction and follows a completely different route: 3D hand tracking is formulated as an optimization problem whose solution is the hand configuration that maximizes the color  ...  Acknowledgments This work was partially supported by the projects Co4Robots (H2020-ICT-2016-1-731869) and WEARHAP (EUFP7-ICT-2011-9-601165).  ... 
doi:10.1109/iccvw.2017.74 dblp:conf/iccvw/PantelerisA17 fatcat:i22cak5ti5fjbcri7qkhfsij3i

Volumetric Hand Reconstructions for Non-verbal Communication in Shared Virtual Environments [article]

Christoph John, Holger Regenbrecht, Ulrich Schwanecke
2010 Eurographics State of the Art Reports  
Dense volume reconstructions of hands based on a probabilistic Shape from Silhouette algorithm are applied for tracking and visualization.  ...  It will be shown, that meshes resulting from probabilistic volume reconstructions thereby exhibit superior detail in comparison to mesh models generated from non-probabilistic comparative approaches which  ...  For visual hull reconstruction now different image based classifiers for fore-/background and skin color detection are combined in a Bayesian framework to compute the MAP estimate for each voxel location  ... 
doi:10.2312/egsh.20101042 fatcat:kpl2moy7lzh45cdnekcsavabnu

Vision-Based Interpretation of Hand Gestures for Remote Control of a Computer Mouse [chapter]

Antonis A. Argyros, Manolis I. A. Lourakis
2006 Lecture Notes in Computer Science  
As confirmed by several experiments, the proposed interface achieves accurate mouse positioning, smooth cursor movement and reliable recognition of gestures activating button events.  ...  Dependable hand tracking, combined with fingertip detection, facilitates the definition of simple and, therefore, robustly interpretable vocabularies of hand gestures that are subsequently used to enable  ...  Acknowledgements This work has been partially supported by EU IST-2001-32184 project Ac-tIPret and EU-IST NoE MUSCLE (FP6-507752).  ... 
doi:10.1007/11754336_5 fatcat:4gp2o7h4afaotgb5d65ctafx4e

Three-dimensional tracking of multiple skin-colored regions by a moving stereoscopic system

Antonis A. Argyros, Manolis I. A. Lourakis
2004 Applied Optics  
A system that performs three-dimensional ͑3D͒ tracking of multiple skin-colored regions ͑SCRs͒ in images acquired by a calibrated, possibly moving stereoscopic rig is described.  ...  Representative experimental results from the application of the SCRT to image sequences are also provided.  ...  This research was partially supported by EU Information Society Technologies project ActIPret ͑IST-2001-32184͒.  ... 
doi:10.1364/ao.43.000366 pmid:14735956 fatcat:suvntaz62rfttcqybjylbnzznm

External Anatomical Shapes Reconstruction from Turntable Image Sequences using a Single off-the-shelf Camera

Teresa Azevedo, João Manuel R. S. Tavares, Mário A. P. Vaz
2008 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
The final goal of the work presented in this paper is to reconstruct all-round 3D models of external anatomical shapes with good accuracy and photorealistic appearance, using a single off-theshelf camera  ...  With those methods, from a turntable image sequence of an object, a 3D model can be built.  ...  FCT -Fundação para a Ciência e a Tecnologia from Portugal.  ... 
doi:10.5565/rev/elcvia.254 fatcat:hnjhsfrk2rbsvf4uxoolh6pxra
« Previous Showing results 1 — 15 out of 60,852 results